From: Shaohua Li <shli@fb.com>
To: <linux-kernel@vger.kernel.org>, <linux-block@vger.kernel.org>
Cc: <axboe@kernel.dk>, <tj@kernel.org>,
Vivek Goyal <vgoyal@redhat.com>, <jmoyer@redhat.com>,
<Kernel-team@fb.com>
Subject: [PATCH V7 09/18] blk-throttle: make throtl_slice tunable
Date: Mon, 27 Mar 2017 10:51:37 -0700 [thread overview]
Message-ID: <0c1c990f15fff70b4c0a5a50984f3803420db3f3.1490634565.git.shli@fb.com> (raw)
In-Reply-To: <cover.1490634565.git.shli@fb.com>
throtl_slice is important for blk-throttling. It's called slice
internally but it really is a time window blk-throttling samples data.
blk-throttling will make decision based on the samplings. An example is
bandwidth measurement. A cgroup's bandwidth is measured in the time
interval of throtl_slice.
A small throtl_slice meanse cgroups have smoother throughput but burn
more CPUs. It has 100ms default value, which is not appropriate for all
disks. A fast SSD can dispatch a lot of IOs in 100ms. This patch makes
it tunable.
Since throtl_slice isn't a time slice, the sysfs name
'throttle_sample_time' reflects its character better.
Signed-off-by: Shaohua Li <shli@fb.com>
---
Documentation/block/queue-sysfs.txt | 6 +++
block/blk-sysfs.c | 11 ++++++
block/blk-throttle.c | 79 ++++++++++++++++++++++++++-----------
block/blk.h | 5 +++
4 files changed, 79 insertions(+), 22 deletions(-)
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index c0a3bb5..b7f6bdc 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -192,5 +192,11 @@ scaling back writes. Writing a value of '0' to this file disables the
feature. Writing a value of '-1' to this file resets the value to the
default setting.
+throttle_sample_time (RW)
+-------------------------
+This is the time window that blk-throttle samples data, in millisecond.
+blk-throttle makes decision based on the samplings. Lower time means cgroups
+have more smooth throughput, but higher CPU overhead. This exists only when
+CONFIG_BLK_DEV_THROTTLING_LOW is enabled.
Jens Axboe <jens.axboe@oracle.com>, February 2009
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index fa831cb..b315e62 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -677,6 +677,14 @@ static struct queue_sysfs_entry queue_wb_lat_entry = {
.store = queue_wb_lat_store,
};
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+static struct queue_sysfs_entry throtl_sample_time_entry = {
+ .attr = {.name = "throttle_sample_time", .mode = S_IRUGO | S_IWUSR },
+ .show = blk_throtl_sample_time_show,
+ .store = blk_throtl_sample_time_store,
+};
+#endif
+
static struct attribute *default_attrs[] = {
&queue_requests_entry.attr,
&queue_ra_entry.attr,
@@ -710,6 +718,9 @@ static struct attribute *default_attrs[] = {
&queue_dax_entry.attr,
&queue_wb_lat_entry.attr,
&queue_poll_delay_entry.attr,
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ &throtl_sample_time_entry.attr,
+#endif
NULL,
};
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 2073b48..93841da 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -19,7 +19,8 @@ static int throtl_grp_quantum = 8;
static int throtl_quantum = 32;
/* Throttling is performed over 100ms slice and after that slice is renewed */
-static unsigned long throtl_slice = HZ/10; /* 100 ms */
+#define DFL_THROTL_SLICE (HZ / 10)
+#define MAX_THROTL_SLICE (HZ)
static struct blkcg_policy blkcg_policy_throtl;
@@ -162,6 +163,8 @@ struct throtl_data
/* Total Number of queued bios on READ and WRITE lists */
unsigned int nr_queued[2];
+ unsigned int throtl_slice;
+
/* Work for dispatching throttled bios */
struct work_struct dispatch_work;
unsigned int limit_index;
@@ -590,7 +593,7 @@ static void throtl_dequeue_tg(struct throtl_grp *tg)
static void throtl_schedule_pending_timer(struct throtl_service_queue *sq,
unsigned long expires)
{
- unsigned long max_expire = jiffies + 8 * throtl_slice;
+ unsigned long max_expire = jiffies + 8 * sq_to_tg(sq)->td->throtl_slice;
/*
* Since we are adjusting the throttle limit dynamically, the sleep
@@ -658,7 +661,7 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg,
if (time_after_eq(start, tg->slice_start[rw]))
tg->slice_start[rw] = start;
- tg->slice_end[rw] = jiffies + throtl_slice;
+ tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
throtl_log(&tg->service_queue,
"[%c] new slice with credit start=%lu end=%lu jiffies=%lu",
rw == READ ? 'R' : 'W', tg->slice_start[rw],
@@ -670,7 +673,7 @@ static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw)
tg->bytes_disp[rw] = 0;
tg->io_disp[rw] = 0;
tg->slice_start[rw] = jiffies;
- tg->slice_end[rw] = jiffies + throtl_slice;
+ tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
throtl_log(&tg->service_queue,
"[%c] new slice start=%lu end=%lu jiffies=%lu",
rw == READ ? 'R' : 'W', tg->slice_start[rw],
@@ -680,13 +683,13 @@ static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw)
static inline void throtl_set_slice_end(struct throtl_grp *tg, bool rw,
unsigned long jiffy_end)
{
- tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+ tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice);
}
static inline void throtl_extend_slice(struct throtl_grp *tg, bool rw,
unsigned long jiffy_end)
{
- tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+ tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice);
throtl_log(&tg->service_queue,
"[%c] extend slice start=%lu end=%lu jiffies=%lu",
rw == READ ? 'R' : 'W', tg->slice_start[rw],
@@ -726,19 +729,20 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
* is bad because it does not allow new slice to start.
*/
- throtl_set_slice_end(tg, rw, jiffies + throtl_slice);
+ throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice);
time_elapsed = jiffies - tg->slice_start[rw];
- nr_slices = time_elapsed / throtl_slice;
+ nr_slices = time_elapsed / tg->td->throtl_slice;
if (!nr_slices)
return;
- tmp = tg_bps_limit(tg, rw) * throtl_slice * nr_slices;
+ tmp = tg_bps_limit(tg, rw) * tg->td->throtl_slice * nr_slices;
do_div(tmp, HZ);
bytes_trim = tmp;
- io_trim = (tg_iops_limit(tg, rw) * throtl_slice * nr_slices) / HZ;
+ io_trim = (tg_iops_limit(tg, rw) * tg->td->throtl_slice * nr_slices) /
+ HZ;
if (!bytes_trim && !io_trim)
return;
@@ -753,7 +757,7 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
else
tg->io_disp[rw] = 0;
- tg->slice_start[rw] += nr_slices * throtl_slice;
+ tg->slice_start[rw] += nr_slices * tg->td->throtl_slice;
throtl_log(&tg->service_queue,
"[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu",
@@ -773,9 +777,9 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
/* Slice has just started. Consider one slice interval */
if (!jiffy_elapsed)
- jiffy_elapsed_rnd = throtl_slice;
+ jiffy_elapsed_rnd = tg->td->throtl_slice;
- jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
+ jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
/*
* jiffy_elapsed_rnd should not be a big value as minimum iops can be
@@ -822,9 +826,9 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
/* Slice has just started. Consider one slice interval */
if (!jiffy_elapsed)
- jiffy_elapsed_rnd = throtl_slice;
+ jiffy_elapsed_rnd = tg->td->throtl_slice;
- jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
+ jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
tmp = tg_bps_limit(tg, rw) * jiffy_elapsed_rnd;
do_div(tmp, HZ);
@@ -890,8 +894,10 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw]))
throtl_start_new_slice(tg, rw);
else {
- if (time_before(tg->slice_end[rw], jiffies + throtl_slice))
- throtl_extend_slice(tg, rw, jiffies + throtl_slice);
+ if (time_before(tg->slice_end[rw],
+ jiffies + tg->td->throtl_slice))
+ throtl_extend_slice(tg, rw,
+ jiffies + tg->td->throtl_slice);
}
if (tg_with_in_bps_limit(tg, bio, &bps_wait) &&
@@ -1632,7 +1638,7 @@ static bool throtl_can_upgrade(struct throtl_data *td,
if (td->limit_index != LIMIT_LOW)
return false;
- if (time_before(jiffies, td->low_downgrade_time + throtl_slice))
+ if (time_before(jiffies, td->low_downgrade_time + td->throtl_slice))
return false;
rcu_read_lock();
@@ -1689,8 +1695,9 @@ static bool throtl_tg_can_downgrade(struct throtl_grp *tg)
* If cgroup is below low limit, consider downgrade and throttle other
* cgroups
*/
- if (time_after_eq(now, td->low_upgrade_time + throtl_slice) &&
- time_after_eq(now, tg_last_low_overflow_time(tg) + throtl_slice))
+ if (time_after_eq(now, td->low_upgrade_time + td->throtl_slice) &&
+ time_after_eq(now, tg_last_low_overflow_time(tg) +
+ td->throtl_slice))
return true;
return false;
}
@@ -1719,13 +1726,14 @@ static void throtl_downgrade_check(struct throtl_grp *tg)
return;
if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
return;
- if (time_after(tg->last_check_time + throtl_slice, now))
+ if (time_after(tg->last_check_time + tg->td->throtl_slice, now))
return;
elapsed_time = now - tg->last_check_time;
tg->last_check_time = now;
- if (time_before(now, tg_last_low_overflow_time(tg) + throtl_slice))
+ if (time_before(now, tg_last_low_overflow_time(tg) +
+ tg->td->throtl_slice))
return;
if (tg->bps[READ][LIMIT_LOW]) {
@@ -1953,6 +1961,7 @@ int blk_throtl_init(struct request_queue *q)
q->td = td;
td->queue = q;
+ td->throtl_slice = DFL_THROTL_SLICE;
td->limit_valid[LIMIT_MAX] = true;
td->limit_index = LIMIT_MAX;
@@ -1973,6 +1982,32 @@ void blk_throtl_exit(struct request_queue *q)
kfree(q->td);
}
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page)
+{
+ if (!q->td)
+ return -EINVAL;
+ return sprintf(page, "%u\n", jiffies_to_msecs(q->td->throtl_slice));
+}
+
+ssize_t blk_throtl_sample_time_store(struct request_queue *q,
+ const char *page, size_t count)
+{
+ unsigned long v;
+ unsigned long t;
+
+ if (!q->td)
+ return -EINVAL;
+ if (kstrtoul(page, 10, &v))
+ return -EINVAL;
+ t = msecs_to_jiffies(v);
+ if (t == 0 || t > MAX_THROTL_SLICE)
+ return -EINVAL;
+ q->td->throtl_slice = t;
+ return count;
+}
+#endif
+
static int __init throtl_init(void)
{
kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0);
diff --git a/block/blk.h b/block/blk.h
index d1ea4bd9..bcd3de6 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -324,5 +324,10 @@ static inline void blk_throtl_drain(struct request_queue *q) { }
static inline int blk_throtl_init(struct request_queue *q) { return 0; }
static inline void blk_throtl_exit(struct request_queue *q) { }
#endif /* CONFIG_BLK_DEV_THROTTLING */
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
+extern ssize_t blk_throtl_sample_time_store(struct request_queue *q,
+ const char *page, size_t count);
+#endif
#endif /* BLK_INTERNAL_H */
--
2.9.3
next prev parent reply other threads:[~2017-03-27 18:37 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-27 17:51 [PATCH V7 00/18] blk-throttle: add .low limit Shaohua Li
2017-03-27 17:51 ` [PATCH V7 01/18] blk-throttle: use U64_MAX/UINT_MAX to replace -1 Shaohua Li
2017-03-27 17:51 ` [PATCH V7 02/18] blk-throttle: prepare support multiple limits Shaohua Li
2017-03-27 17:51 ` [PATCH V7 03/18] blk-throttle: add configure option for new .low interface Shaohua Li
2017-03-27 17:51 ` [PATCH V7 04/18] blk-throttle: add " Shaohua Li
2017-03-27 17:51 ` [PATCH V7 05/18] blk-throttle: configure bps/iops limit for cgroup in low limit Shaohua Li
2017-03-27 17:51 ` [PATCH V7 06/18] blk-throttle: add upgrade logic for LIMIT_LOW state Shaohua Li
2017-03-27 17:51 ` [PATCH V7 07/18] blk-throttle: add downgrade logic Shaohua Li
2017-03-27 17:51 ` [PATCH V7 08/18] blk-throttle: make sure expire time isn't too big Shaohua Li
2017-03-27 17:51 ` Shaohua Li [this message]
2017-03-27 17:51 ` [PATCH V7 10/18] blk-throttle: choose a small throtl_slice for SSD Shaohua Li
2017-03-27 17:51 ` [PATCH V7 11/18] blk-throttle: detect completed idle cgroup Shaohua Li
2017-03-27 17:51 ` [PATCH V7 12/18] blk-throttle: make bandwidth change smooth Shaohua Li
2017-03-27 17:51 ` [PATCH V7 13/18] blk-throttle: add a simple idle detection Shaohua Li
2017-03-27 17:51 ` [PATCH V7 14/18] blk-throttle: add interface to configure idle time threshold Shaohua Li
2017-03-27 17:51 ` [PATCH V7 15/18] blk-throttle: ignore idle cgroup limit Shaohua Li
2017-03-27 17:51 ` [PATCH V7 16/18] blk-throttle: add interface for per-cgroup target latency Shaohua Li
2017-03-27 17:51 ` [PATCH V7 17/18] blk-throttle: add a mechanism to estimate IO latency Shaohua Li
2017-03-27 17:51 ` [PATCH V7 18/18] blk-throttle: add latency target support Shaohua Li
2017-03-27 18:15 ` [PATCH V7 00/18] blk-throttle: add .low limit Jens Axboe
2017-03-27 19:00 ` Shaohua Li
2017-03-27 19:11 ` Jens Axboe
2017-03-27 22:19 ` [PATCH 0/3] blk-throttle: add .low limit fix Shaohua Li
2017-03-27 22:19 ` [PATCH 1/3] block: track request size in blk_issue_stat Shaohua Li
2017-03-27 22:19 ` [PATCH 2/3] blk-throttle: add a mechanism to estimate IO latency Shaohua Li
2017-03-27 22:19 ` [PATCH 3/3] blk-throttle: add latency target support Shaohua Li
2017-03-28 15:58 ` [PATCH 0/3] blk-throttle: add .low limit fix Jens Axboe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=0c1c990f15fff70b4c0a5a50984f3803420db3f3.1490634565.git.shli@fb.com \
--to=shli@fb.com \
--cc=Kernel-team@fb.com \
--cc=axboe@kernel.dk \
--cc=jmoyer@redhat.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=tj@kernel.org \
--cc=vgoyal@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).